Abstract
An accurate forecast of the power generated by a wind turbine is of paramount importance for its optimal exploitation. Several forecasting methods have been proposed either based on a physical modeling or using a statistical approach. All of them rely on the availability of high quality measures of local wind speed, corresponding generated power and on numerical weather forecasts. In this paper, a simple and effective wind power forecast technique, based on the probability distribution mapping of wind speed forecast and observed power data, is presented and it is applied to two turbines located on the island of Borkum (Germany) in the North Sea. The wind speed forecast of the ECMWF model at 100 m from the ground is used as the prognostic meteorological parameter. Training procedures are based entirely on relatively short time series of power measurements. Results show that our approach has skills that are similar or better than those obtained using more standard methods when measured with mean absolute error.
Highlights
The production of energy from wind has become economically and technically viable, with high potential for growth
A reasonable way to choose the "most probable" response curve of the turbine as a function of the wind speed forecast is along the line that bisects the copula space and where the bivariate distribution C (u, v) has its maximum. This line pairs the quantiles of wind speed with the same quantiles of the power production and in the space of physical variables is what we have indicated as dm
For the ann and knn models, the wind speeds at 10 m, 100 m and wind gust at 10 m above ground are considered, while for the dm, mean and median models, only the wind speed at 100 m have been used
Summary
The production of energy from wind has become economically and technically viable, with high potential for growth. Energy storage and generation forecasts are the most attractive strategies for a small grid, and in particular for use on an island These procedures are one of the subjects studied in the European NETfficient project (http://www.netfficient-project.eu), to which this work is related. The model is obtained under controlled conditions by simultaneously measuring the power generated and the wind speed at the turbine hub height, and using a regression procedure between these two data sets. The limit of this curve is related to the standard conditions under which it is obtained. It was observed that there could be notable discrepancies between manufacturer’s power curves and the test results carried out at high wind speeds [24]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
